Presentation 1998/10/14
Credit Risk Manegement by Using Decision Tree with Region Rules
Yasuhiko Morimoto, Takeshi Fukuda, Hirofumi Matsuzawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Estimating risk of default is one of the most important issue of the credit risk management in financial community. The authors constructed a decision tree that discreminates between risky and safe companies by using financial statements and estimate the credit risk using the tree model. Financial data contain many numeric attributes that are correlated with each other. However, conventional data mining techniques cannot handle correlations well. In this paper, we point out the importance of handling correlations in mining financial data, and propose a region rules for handling correlations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Data Mining / Decision Tree / Financial Statements Analysis / Credit Risk
Paper # DE98-13
Date of Issue

Conference Information
Committee DE
Conference Date 1998/10/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Credit Risk Manegement by Using Decision Tree with Region Rules
Sub Title (in English)
Keyword(1) Data Mining
Keyword(2) Decision Tree
Keyword(3) Financial Statements Analysis
Keyword(4) Credit Risk
1st Author's Name Yasuhiko Morimoto
1st Author's Affiliation IBM Japan, Tokyo Research Laboratory()
2nd Author's Name Takeshi Fukuda
2nd Author's Affiliation IBM Japan, Tokyo Research Laboratory
3rd Author's Name Hirofumi Matsuzawa
3rd Author's Affiliation IBM Japan, Tokyo Research Laboratory
Date 1998/10/14
Paper # DE98-13
Volume (vol) vol.98
Number (no) 316
Page pp.pp.-
#Pages 8
Date of Issue